Knowledge base

Real-Time Data with Microsoft Fabric & Spark

In this insight, we will show you how to create and set up an efficient streaming pipeline using Microsoft Fabric. No more struggling with slow and inaccurate data streams - with our step-by-step process, you can easily set up a robust and lightning-fast pipeline that will deliver real-time insights like never before. Whether you're a seasoned pro or starting this insightful guide will help you take your data-handling skills to the next level.

Lundi, 12 février 2024

Can Power BI DAX Query view replace DAX Studio? Not quite, but…

Introduction Everybody who's been working with Power BI has heard (or should have heard) about another great tool, called Dax Studio. If you want a powerful way to look at the measures of a model, look deeper into performance, view the metrics of your model to figure out if there is nothing there slowing you down or eating up valuable space, etc. DAX Studio was and is still the go-to tool.

Dirk Meert

Mercredi, 7 février 2024

How to include OT data in a scalable and reliable Data Platform with Azure and Lambda Architecture

OT data in the Modern Data Platform on Azure Many production companies today have extensive OT architectures that digitalize and manage their production process. A lot of data flows through this OT setup, which is often undervalued and underused for analytics.

Louis Vincent

Mardi, 30 janvier 2024

Amaze the CFO with these custom financial Tables & Matrices

This insight aims to explore the nuances of implementing custom table structures in Power BI for financial reporting, shedding light on the methodology, benefits, and potential challenges associated with this advanced analytical technique. By understanding and harnessing the power of custom tables, organizations can unlock a new level of precision in their financial analyses, leading to more informed decision-making and strategic planning.

Justine Decuypere

Justine Decuypere

Lundi, 29 janvier 2024

Boost Big Data Analysis with Databricks, Marketplace & Mistral

More than a year ago OpenAI released ChatGPT and the entire world seems to be using it, then they released different models and many people are also paying for premium features with a monthly fee, however OpenAI models are all behind a REST API which sooner or later you as an AI Developer will face some limitations. Whether you use OpenAI public endpoints or Azure OpenAI Endpoints, in both flavors the models are exposed as REST API and the limitations in terms of scaling are the same.

Luis Valencia

Jeudi, 25 janvier 2024

GPT Store: The "Apple Store" for GPTs

Last week OpenAI announced the launch of their GPT Store. Let's have a look at what this GPT Store exactly is and how it can impact your business.

Konstantin Lazarov

Konstantin Lazarov

Peter Depypere

Joran Vergauwen

Joran Vergauwen

Vendredi, 19 janvier 2024

Du langage à la connaissance: le chatbot de Qlik Sense révolutionne l'exploration des données

Dans le monde d'aujourd'hui, dominé par les données, les entreprises s'appuient sur des outils et des technologies de pointe pour extraire des informations précieuses de leurs données. Qlik Sense, acteur majeur dans le domaine de la veille stratégique et de l'analyse de données, a introduit une fonctionnalité innovante appelée « Insight Advisor » pour aider les utilisateurs à exploiter la puissance des données avec une facilité inégalée. Bien que l'Insight Advisor offre un large éventail de fonctionnalités, cet article se penchera plus en détail sur l'un de ses aspects les plus fascinants : l'interaction en langage naturel : L'interaction en langage naturel, soutenue par un modèle logique et un vocabulaire de logique d'entreprise.

Stan Decoene

Mardi, 16 janvier 2024

Mistral: The French Revolution of Generative AI

The generative AI field is a fast-paced, continuously changing landscape that is dominated by the United States and China. To combat this dominance, European-based companies are increasingly recognizing the importance of creating their own Large Language Models (LLMs) trained on European data. This allows for the development of models fluent in the most widely spoken European languages, as opposed to LLMs only trained on English/American data. Several EU-based companies, often supported by major corporations and governments, have taken up the challenge of developing European LLMs. We investigated one of them called Mistral and explored how their models compare to the well-known American Models.

Konstantin Lazarov

Konstantin Lazarov

Peter Depypere

Joran Vergauwen

Joran Vergauwen

Jeudi, 11 janvier 2024

Will AI Extinguish Code Developers

Using state-of-the-art LLMs to generate a bunch of potential solutions to a complex coding problem, and a verifier to select the best solution, the ability to solve these problems can be increased tremendously. Going forward, the tradeoff between larger models and this generation - verification mechanism will be important for the scalability of these LLM systems. While it looks like AlphaCode2 is already better at solving complex coding problems than most humans, there is still a synergy to be found between human and machine. The role of developers might change from actual hands-on coding to a role that more revolves around instructing the LLMs, safeguarding best practices and explaining the results to the business

Joran Vergauwen

Joran Vergauwen

Peter Depypere

Mercredi, 3 janvier 2024

Google Gemini: The Next Big Thing

By launching Gemini, Google emerged on the Gen AI field as a 600 pound contestant to a sumo wrestling match. With flashy demos and astounding performances on various foundation model benchmarks, Google seems to be back in the race for AI dominance. In this post, we aim to shed a light on what Gemini actually entails and whether or not it is as great as Google wants us to believe.

Joran Vergauwen

Joran Vergauwen

Peter Depypere

Mardi, 19 décembre 2023